Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Automatic image annotation and translation method based on decision tree learning

An automatic image and decision tree technology, applied in special data processing applications, instruments, electrical digital data processing, etc., can solve problems such as incompatibility with image databases, incomplete databases, and noisy data.

Inactive Publication Date: 2010-01-06
SOUTHWEST JIAOTONG UNIV
View PDF1 Cites 26 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In view of the above deficiencies in the prior art, the purpose of the present invention is to study a method for automatic image labeling and translation based on decision tree learning, so that the training set after labeling has scalability and robustness, to solve the problem of training image database Problems with not fitting to another untrained image database and problems with incomplete and noisy data

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Automatic image annotation and translation method based on decision tree learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0035] Given 5100 Corel database images, 570 images of 19×30 are selected as the training image set of the method of the present invention, and the embodiment performs automatic image labeling on the remaining images.

[0036] (1) Segment all images in the training image set to form several image sub-blocks (regions), extract color, texture, and shape features from the image sub-blocks, and obtain feature data x 1 , x 2 ,...,x L (L-dimensional color feature), y 1 ,y 2 ,...,y M (M-dimensional texture features), z 1 ,z 2 ,...,z N (N-dimensional shape features).

[0037] In the stage of discretization of eigenvalues ​​processed by adaptive VQ, taking color features as an example, the first step is to calculate the initial clustering center, let this center be c 1 , and then set the initial number of clusters CN=1; the second step first selects the cluster centers that exceed the L-dimensional color feature, let n be the number of selected centers, if n=0, stop, otherwise ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses an automatic image annotation and translation method based on decision tree learning. A new image is automatically annotated, and a text word list with a visualized content is translated by a machine so as to realize the machine retrieval of image data, comprising a training annotation image set and image automatic annotations, wherein the training annotation image set utilizes an image segmentation algorithm to segment a training image set into sub areas and extract low-level visual features of each sub area; the feature data is discretized, and then the training annotation image set is classified by a clustering algorithm based on a low-level feature discrete value to construct a semantic dictionary; the low-level feature discrete value is used as an input attribute of the decision tree learning; and self training learning is carried out on the constructed dictionary by a decision tree machine learning corresponding to preset semantic concepts so as to generate a decision tree and obtain a corresponding decision rule. The training annotation image set has expandability and robustness and can improve the recall ratio and the precision ratio of the retrieval when the training annotation image set is applied to semantic image retrievals.

Description

technical field [0001] The invention relates to the fields of digital image retrieval technology and machine learning technology, in particular to a method for automatic image labeling and translation based on decision tree learning. Background technique [0002] In the early days, people realized image retrieval through manual annotation, but this work was time-consuming and laborious, especially when faced with large-scale network images, it was obviously not competent. Therefore, how to quickly and effectively realize the automatic semantic annotation of images has become very necessary. [0003] Automatic image annotation is a process of automatically assigning metadata to a digital image in the form of captions or keywords by a computer system. This computer vision application technique is used in image retrieval to organize and find images of interest to the user in the database. This method is called a multi-class image classification method, which contains a large ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06F17/30G06N1/00
Inventor 侯进张登胜
Owner SOUTHWEST JIAOTONG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Eureka Blog
Learn More
PatSnap group products